Identifying Fixed Points in Recurrent Neural Networks using Directional Fibers: Supplemental Material on Theoretical Results and Practical Aspects of Numerical Traversal

dc.contributor.authorKatz, Garrett
dc.contributor.authorReggia, James
dc.date.accessioned2016-12-13T02:54:12Z
dc.date.available2016-12-13T02:54:12Z
dc.date.issued2016-12-12
dc.description.abstractFixed points of recurrent neural networks can represent many things, including stored memories, solutions to optimization problems, and waypoints along non-fixed attractors. As such, they are relevant to a number of neurocomputational phenomena, ranging from low-level motor control and tool use to high-level problem solving and decision making. Therefore, global solution of the fixed point equations can improve our understanding and engineering of recurrent neural networks. While local solvers and statistical characterizations abound, we do not know of any method for efficiently and precisely locating all fixed points of an arbitrary network. To solve this problem we have proposed a novel strategy for global fixed point location, based on numerical traversal of mathematical objects we defined called directional fibers [2]. This report supplements our results in [2] by presenting certain technical aspects of our method in more depth.en_US
dc.identifierhttps://doi.org/10.13016/M2HJ97
dc.identifier.urihttp://hdl.handle.net/1903/18918
dc.language.isoen_USen_US
dc.relation.ispartofseriesUM Computer Science Department;CS-TR-5051
dc.titleIdentifying Fixed Points in Recurrent Neural Networks using Directional Fibers: Supplemental Material on Theoretical Results and Practical Aspects of Numerical Traversalen_US
dc.typeTechnical Reporten_US

Files

Original bundle

Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
CS-TR-5051-rev1.pdf
Size:
379.39 KB
Format:
Adobe Portable Document Format
Description: